Out of their minds: legal theory in neural networks

This paper examines the use of connectionism (neural networks) in modelling legal reasoning. I discuss how the implementations of neural networks have failed to account for legal theoretical perspectives on adjudication. I criticise the use of neural networks in law, not because connectionism is inherently unsuitable in law, but rather because it has been done so poorly to date. The paper reviews a number of legal theories which provide a grounding for the use of neural networks in law. It then examines some implementations undertaken in law and criticises their legal theoretical naïvete. It then presents a lessons from the implementations which researchers must bear in mind if they wish to build neural networks which are justified by legal theories.     

The computational metaphor and environmentalism

The Computational Metaphor is an extremely influential notion, and more than any other trend has given rise to the field of Cognitive Science. Environmentalism is at present better formalised as a political movement than as a scientific paradigm, despite significant research by Gibson and his followers. This article attempts to address the difficult problem of synthesising these two apparently antagonistic research paradigms.     

Simulation of heterogeneous neural networks on serial and parallel machines

There has recently been a tremendous rebirth of interest in neural networks, ranging from distributed and localist spreading-activation networks to semantic networks with symbolic marker-passing. Ideally these networks would be encoded in dedicated massively-parallel hardware that directly implements their functionality. Cost and flexibility concerns, however, necessitate the use of general-purpose machines the simulate neural networks, especially in the research stages in which various models are being explored and tested. Issues of a simulation's timing and control become more critical when models are made up of heterogeneous networks in which nodes have different processing characteristics and cycling rates or which are made up of modular, interacting sub-networks. We have developed a simulation environment to create, operate, and control these types of connectionist networks. This paper describes how massively-parallel heterogeneous networks are simulated on serial machines as efficiently as possible, how large-scale simulations could be handled on current SIMD parallel machines, and outlines how the simulator could be implemented on its ideal hardware, a large-scale MIMD parallel machine.     

The Causal and Explanatory Role of Information Stored in Connectionist Networks

In this paper I defend the propriety of explaining the behavior of distributed connectionist networks by appeal to selected data stored therein. In particular, I argue that if there is a problem with such explanations, it is a consequence of the fact that information storage in networks is superpositional, and not because it is distributed. I then develop a ``proto-account' of causation for networks, based on an account of Andy Clark's, that shows even superpositionality does not undermine information-based explanation. Finally, I argue that the resulting explanations are genuinely informative and not vacuous.     

Cognition and the Power of Continuous Dynamical Systems

Traditional approaches to modeling cognitive systems are computational, based on utilizing the standard tools and concepts of the theory of computation. More recently, a number of philosophers have argued that cognition is too subtle or complex for these tools to handle. These philosophers propose an alternative based on dynamical systems theory. Proponents of this view characterize dynamical systems as (i) utilizing continuous rather than discrete mathematics, and, as a result, (ii) being computationally more powerful than traditional computational automata. Indeed, the logical possibility of such super-powerful systems has been demonstrated in the form of analog artificial neural networks. In this paper I consider three arguments against the nomological possibility of these automata. While the first two arguments fail, the third succeeds. In particular, the presence of noise reduces the computational power of analog networks to that of traditional computational automata, and noise is a pervasive feature of information processing in biological systems. Consequently, as an empirical thesis, the proposed dynamical alternative is under-motivated: What is required is an account of how continuously valued systems could be realized in physical systems despite the ubiquity of noise.     

Two Apparent ‘Counterexamples’ To Marcus: A Closer Look

Marcus et al.’s experiment (1999) concerning infant ability to distinguish between differing syntactic structures has prompted connectionists to strive to show that certain types of neural networks can mimic the infants’ results. In this paper we take a closer look at two such attempts: Shultz and Bale [Shultz, T.R. and Bale, A.C. (2001), Infancy 2, pp. 501–536] Altmann and Dienes [Altmann, G.T.M. and Dienes, Z. (1999) Science 248, p. 875a]. We were not only interested in how well these two models matched the infants’ results, but also whether they were genuinely learning the grammars involved in this process. After performing an extensive set of experiments, we found that, at first blush, Shultz and Bale’s model (2001) replicated the infant’s known data, but the model largely failed to learn the grammars. We also found serious problems with Altmann and Dienes’ model (1999), which fell short of matching any of the infant’s results and of learning the syntactic structure of the input patterns.     

Neural Networks and Structured Knowledge: Rule Extraction and Applications

As the second part of a special issue on Neural Networks and Structured Knowledge, the contributions collected here concentrate on the extraction of knowledge, particularly in the form of rules, from neural networks, and on applications relying on the representation and processing of structured knowledge by neural networks. The transformation of the low-level internal representation in a neural network into higher-level knowledge or information that can be interpreted more easily by humans and integrated with symbol-oriented mechanisms is the subject of the first group of papers. The second group of papers uses specific applications as starting point, and describes approaches based on neural networks for the knowledge representation required to solve crucial tasks in the respective application.The companion first part of the special issue [1] contains papers dealing with representation and reasoning issues on the basis of neural networks.     

Neural Networks and Structured Knowledge: Knowledge Representation and Reasoning

This collection of articles is the first of two parts of a special issue on Neural Networks and Structured Knowledge. The contributions to the first part shed some light on the issues of knowledge representation and reasoning with neural networks. Their scope ranges from formal models for mapping discrete structures like graphs or logical formulae onto different types of neural networks, to the construction of practical systems for various types of reasoning. In the second part to follow, the emphasis will be on the extraction of knowledge from neural networks, and on applications of neural networks and structured knowledge to practical tasks.     

Symbolic and Neural Learning Algorithms: An Experimental Comparison

Despite the fact that many symbolic and neural network (connectionist) learning algorithms address the same problem of learning from classified examples, very little is known regarding their comparative strengths and weaknesses. Experiments comparing the ID3 symbolic learning algorithm with the perception and backpropagation neural learning algorithms have been performed using five large, real-world data sets. Overall, backpropagation performs slightly better than the other two algorithms in terms of classification accuracy on new examples, but takes much longer to train. Experimental results suggest that backpropagation can work significantly better on data sets containing numerical data. Also analyzed empirically are the effects of (1) the amount of training data, (2) imperfect training examples, and (3) the encoding of the desired outputs. Backpropagation occasionally outperforms the other two systems when given relatively small amounts of training data. It is slightly more accurate than ID3 when examples are noisy or incompletely specified. Finally, backpropagation more effectively utilizes a distributed output encoding.     

Computational theories of mind,and Fodor's analysis of neural network behaviour

The purpose of this paper is to examine critically Jerry Fodor's views of the limits of computational neural network approaches to understand intelligence. Fodor distinguishes between two different approaches to computationally modelling intelligence, and while he raises problems with both, he is more concerned with the approach taken by those who make use of neural network models of intelligence or cognition. Fodor's claims regarding neural networks are found wanting, and the implications of these shortcomings for computational modelling of cognition are discussed.     

A comparison of connectionist models of music recognition and human performance

Current artificial neural network or connectionist models of music cognition embody feature-extraction and feature-weighting principles. This paper reports two experiments which seek evidence for similar processes mediating recognition of short musical compositions by musically trained and untrained listeners. The experiments are cast within a pattern recognition framework based on the vision-audition analogue wherein music is considered an auditory pattern consisting of local and global features. Local features such as inter-note interval, and global features such as melodic contour, are derived from a two-dimensional matrix in which music is represented as a series of frequencies plotted over time.Manipulation of inter-note interval affected accuracy and reaction time measures in a discrimination task, whereas the same variables were affected by manipulation of melodic contour in a classification task. Musical training is thought of as a form of practice in musical pattern recognition and, as predicted, accuracy and reaction time measures of musically trained subjects were significantly better than those of untrained subjects. Given the evidence for feature-extraction and weighting processes in music recognition tasks, two connectionist models are discussed. The first is a single-layer perceptron which has been trained to discriminate between compositions according to inter-note interval. A second network, using the back-propagation algorithm and sequential input of patterns, is also discussed.     

Automated knowledge acquisition for design and manufacturing: The case of micromachined atomizer

In order to remain competitive in the global market, original equipment manufacturers (OEMs) are developing a process-based, knowledge-driven product development environment with emphasis on the acquisition, storing, and utilization of manufacturing knowledge. This is usually achieved by using the symbolic artificial intelligence (AI) approach. Specifically, knowledge-based expert systems are developed to capture human expertise, mostly in terms of IF–THEN production rules. It has been recognized that the development of symbolic knowledge-based expert systems suffers from the so-called knowledge acquisition bottleneck. Knowledge acquisition is the process of collecting domain knowledge and transforming the knowledge into a computerized representation. It is a challenging and time-consuming process due to the difficulties involved in eliciting knowledge from human experts. This paper presents an automated approach for knowledge acquisition by integrating neural networks learning ability and fuzzy logics structured knowledge representation. Using this approach, knowledge is automatically acquired from data and represented using humanly intelligible fuzzy rules. The approach is applied to a case study of the design and manufacturing of micromachined atomizers for gas turbine engine. The influence of geometric features on the performance of the atomizers is investigated. The results are then compared with those obtained using traditional regression analysis approach (abstract mathematical models). It was found that the automated approach provides an efficient means for knowledge acquisition. Since the fuzzy rules extracted are easy to understand, they can be used to allow more clear specification of manufacturing processes and to shorten learning curves for novice manufacturing engineers.     

浅谈计算机网络工程的质量控制

计算机网络工程一般由多种业务组成,需要运用多种学科的知识和技术来解决问题.项目执行中有许多未知因素,每个因素又有可能带有不确定,需要把具有不同经历的人员组织在一个临时性的团队内,在费用、进度等较为严格的约束条件下,实现预定的目标.大型的计算机网络工程有时由若干个子项目构成,这些子项目还有可能包含若干有逻辑顺序关系的工作单元.这样子项目、工作单元等子系统相互制约和相互依存共同构成完整的项目系统.这些因素决定了计算机网络工程项目管理是一项复杂的工作.     

Validating a neural network application: The case of financial diagnosis

It has been argued that neural network applications should be benchmarked using several data sets of realistic and real problems, and competing algorithms (Prechelt, 1995). However, if applying a neural network model to a particular real problem is in focus, validation should be considered as a suitability evaluation in which several bases of evaluation are combined in a composite judgment. In this paper, five bases of such evaluation are introduced and applied to the validation of a neural network model of financial diagnosis.     

浅析计算机网络安全隐患及防范策略

随着科学技术水平的提升,当前计算机网络已经渗透到我们生活各个领域,影响着我们的工作学习方式,与此同时,网络安全问题也愈发的凸显出来。因为计算机网路自身的开放性质,很容易出现各方面的安全隐患,所以了解计算机网络安全问题的发生原因,并针对性的实施可行措施予以防范应对,是计算机专业领域的关键任务。     

The effects of visual metaphor and cognitive style for mental modeling in a hypermedia-based environment

With the exponential growth of Internet technology, the notion of users’ cognition when navigating such a vast information space has gained prominence. Studies suggest that metaphors can serve as effective tools to scaffold users’ mental modeling processes. However, how users conceive of the metaphorical aid (as opposed to simply how they perceive it) remains questionable. Cognitive style, or the user’s preferred way of information processing, has thus been posited as a possible factor affecting the success of the metaphorical approach in a hypermedia environment.

This study explores the effects of visual metaphors and cognitive styles on users’ learning performances in terms of structural knowledge and feelings of disorientation. The results indicate that a visual metaphor could improve the quality of mental formation, yet simultaneously increase users’ mental load during navigation. In addition, cognitive style is a crucial factor that can significantly affect users’ learning performance.     

On the artificiality of artificial intelligence

In this article the question is raised whether artificial intelligence has any psychological relevance, i.e. contributes to our knowledge of how the mind/brain works. It is argued that the psychological relevance of artificial intelligence of the symbolic kind is questionable as yet, since there is no indication that the brain structurally resembles or operates like a digital computer. However, artificial intelligence of the connectionist kind may have psychological relevance, not because the brain is a neural network, but because connectionist networks exhibit operating characteristics which mimic operant behavior. Finally it is concluded that, since most of the work done so far in AI and Law is of the symbolic kind, it has as yet contributed little to our understanding of the legal mind.     

On-line disciplines: Computer-mediated scholarship in the humanities and social sciences

The recent creation of global-area computer networks invites the development of tools and resources that can reap the scholarly advantages of such technology. In this paper, we discuss prospects for the productive use of computer-mediated communication (CMC) for scholarly interaction. We begin by describing the technology used to deliver information over academic networks and the kinds of disciplinary services that the technology enables. In the second half of the paper we consider factors that bear upon the development of CMC-based disciplinary centers and we call attention to their potential to create a highly interactive form of scholarship.Teresa Harrison and Timothy Stephen are Associate Professors of Communication. Teresa Harrison's research focusses on communication theory and organizational communication. Timothy Stephen specializes in interpersonal communication and the development of community.This research was funded, in part, by the Paul Beer Trust, administered by the School of Humanities and Social Sciences, Rensselaer Polytechnic Institute.